© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 26555
    Prev
    Next
    INDEX
    Explanations

    instances of the term "dash" or equivalent symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    154
    +0.14
    0.8%
    394
    +0.13
    0.7%
    140
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    349
    +0.14
    0.04
    437
    +0.13
    0.04
    247
    +0.12
    0.04
    Negative Logits
    doms
    -1.67
     law
    -1.48
     involved
    -1.44
     awaited
    -1.43
    ony
    -1.42
    ifa
    -1.39
    heid
    -1.39
    uous
    -1.34
    onymous
    -1.32
     attorneys
    -1.32
    POSITIVE LOGITS
    Ļª
    2.98
    §
    2.77
    ľĵ
    2.67
    ¿½
    2.66
    Ń
    2.60
    ĺ
    2.58
    ij
    2.53
    ´
    2.48
    ł
    2.47
    ±
    2.44
    Activations Density 0.032%

    No Known Activations